Image Processing Method and Device, and Storage Medium

Abstract

The present disclosure relates an image processing method and device, and a storage medium. The method comprises: performing a feature equalization processing on a sample image by an equalization subnetwork of a detection network to obtain an equalized feature image of the sample image; performing a target detection processing on the equalized feature image by a detection subnetwork of the detection network to obtain predicted regions of a target object in the equalized feature image; determining an intersection-over-union of each of the predicted regions respectively; sampling the plurality of predicted regions according to the intersection-over-union of each predicted region to obtain a target region; and training the detection network according to the target region and a labeled region. The systems and techniques disclosed here can reduce information loss and improve the training effect and training efficiency.

What is claimed is: 
     
         1 . An image processing method, comprising:
 performing a feature equalization processing on a sample image by an equalization subnetwork of a detection network to obtain an equalized feature image of the sample image, the detection network including the equalization subnetwork and a detection subnetwork;   performing a target detection processing on the equalized feature image by the detection subnetwork to obtain a plurality of predicted regions of a target object in the equalized feature image;   determining an intersection-over-union of each of the plurality of predicted regions respectively, wherein the intersection-over-union is an area ratio of an overlapping region to a merged region of a predicted region of the target object and a corresponding labeled region in the sample image;   sampling the plurality of predicted regions according to the intersection-over-union of each of the predicted regions to obtain a target region; and   training the detection network according to the target region and the labeled region.   
     
     
         2 . The method according to  claim 1 , wherein sampling the plurality of predicted regions according to the intersection-over-union of each of the predicted regions to obtain the target region comprises:
 performing a classification processing on the plurality of predicted regions according to the intersection-over-union of each of the predicted regions to obtain a plurality of categories of predicted regions; and   performing a sampling processing on the predicted regions of each category respectively to obtain the target region.   
     
     
         3 . The method according to  claim 1 , wherein performing the feature equalization processing on the sample image by the equalization subnetwork of the detection network to obtain the equalized feature image comprises:
 performing a feature extraction processing on the sample image to obtain a plurality of first feature maps, wherein a resolution of at least one of the plurality of first feature maps is different from those of other first feature maps;   performing an equalization processing on the plurality of first feature maps to obtain a second feature map; and   obtaining a plurality of equalized feature images according to the second feature map and the plurality of first feature maps.   
     
     
         4 . The method according to  claim 3 , wherein performing the equalization processing on the plurality of first feature maps to obtain the second feature map comprises:
 performing a scaling processing on the plurality of first feature maps respectively to obtain a plurality of third feature maps with preset resolutions;   performing an average processing on the plurality of third feature maps to obtain a fourth feature map; and   performing a feature extraction processing on the fourth feature map to obtain the second feature map.   
     
     
         5 . The method according to  claim 3 , wherein obtaining the plurality of equalized feature images according to the second feature map and the plurality of first feature maps comprises:
 performing a scaling processing on the second feature map to obtain a fifth feature map corresponding to the each first feature map respectively, wherein the first feature map has the same resolution as that of the corresponding fifth feature map; and   performing a residual connection on the each first feature map and the corresponding fifth feature map respectively to obtain the equalized feature image.   
     
     
         6 . The method according to  claim 1 , wherein training the detection network according to the target region and the labeled region comprises:
 determining an identification loss and a location loss of the detection network according to the target region and the labeled region;   adjusting network parameters of the detection network according to the identification loss and the location loss; and   obtaining the trained detection network when training conditions are satisfied.   
     
     
         7 . The method according to  claim 6 , wherein determining the identification loss and the location loss of the detection network according to the target region and the labeled region comprises:
 determining a position error between the target region and the labeled region; and   determining the location loss according to the position error when the position error is less than a preset threshold.   
     
     
         8 . The method according to  claim 6 , wherein determining the identification loss and the location loss of the detection network according to the target region and the labeled region comprises:
 determining a position error between the target region and the labeled region; and   determining the location loss according to a preset value when the position error is larger than or equal to a preset threshold.   
     
     
         9 . The method according to  claim 1 , further comprising:
 inputting an image to be detected into the trained detection network for processing, so as to obtain a position information of the target object.   
     
     
         10 . An image processing device comprising:
 a processor; and   a memory configured to store processor executable instructions,   wherein the processor is configured to:   perform a feature equalization processing on a sample image by an equalization subnetwork of a detection network to obtain an equalized feature image of the sample image, the detection network including the equalization subnetwork and a detection subnetwork;   perform a target detection processing on the equalized feature image by the detection subnetwork to obtain a plurality of predicted regions of a target object in the equalized feature image;   determine an intersection-over-union of each of the plurality of predicted regions respectively, wherein the intersection-over-union is an area ratio of an overlapping region to a merged region of a predicted region of the target object and a corresponding labeled region in the sample image;   sample the plurality of predicted regions according to the intersection-over-union of each of the predicted regions to obtain a target region; and   train the detection network according to the target region and the labeled region.   
     
     
         11 . The device according to  claim 10 , wherein sampling the plurality of predicted regions according to the intersection-over-union of each of the predicted regions to obtain the target region comprises:
 performing a classification processing on the plurality of predicted regions according to the intersection-over-union of each of the predicted regions to obtain a plurality of categories of predicted regions; and   performing a sampling processing on the predicted regions of each category respectively to obtain the target region.   
     
     
         12 . The device according to  claim 10 , wherein performing the feature equalization processing on the sample image by the equalization subnetwork of the detection network to obtain the equalized feature image of the sample image comprises:
 performing a feature extraction processing on the sample image to obtain a plurality of first feature maps, wherein a resolution of at least one of the plurality of first feature maps is different from those of other first feature maps;   performing an equalization processing on the plurality of first feature maps to obtain a second feature map; and   obtaining a plurality of equalized feature images according to the second feature map and the plurality of first feature maps.   
     
     
         13 . The device according to  claim 12 , wherein performing the equalization processing on the plurality of first feature maps to obtain the second feature map comprises:
 performing a scaling processing on the plurality of first feature maps respectively to obtain a plurality of third feature maps with preset resolutions;   performing an average processing on the plurality of third feature maps to obtain a fourth feature map; and   performing a feature extraction processing on the fourth feature map to obtain the second feature map.   
     
     
         14 . The device according to  claim 12 , wherein obtaining the plurality of equalized feature images according to the second feature map and the plurality of first feature maps comprises:
 performing a scaling processing on the second feature map to obtain a fifth feature map corresponding to the each first feature map respectively, wherein the first feature map has the same resolution as that of the corresponding fifth feature map; and   performing a residual connection on the each first feature map and the corresponding fifth feature map respectively to obtain the equalized feature image.   
     
     
         15 . The device according to  claim 10 , wherein training the detection network according to the target region and the labeled region comprises:
 determining an identification loss and a location loss of the detection network according to the target region and the labeled region;   adjusting network parameters of the detection network according to the identification loss and the location loss; and   obtaining the trained detection network when training conditions are satisfied.   
     
     
         16 . The device according to  claim 15 , wherein determining the identification loss and the location loss of the detection network according to the target region and the labeled region comprises:
 determining a position error between the target region and the labeled region; and   determining the location loss according to the position error when the position error is less than a preset threshold.   
     
     
         17 . The device according to  claim 15 , wherein determining the identification loss and the location loss of the detection network according to the target region and the labeled region comprises:
 determining a position error between the target region and the labeled region; and   determining the location loss according to a preset value when the position error is larger than or equal to a preset threshold.   
     
     
         18 . The device according to  claim 10 , wherein the processor is further configured to:
 input an image to be detected into the trained detection network for processing, so as to obtain a position information of the target object.   
     
     
         19 . A computer readable storage medium having computer program instructions stored thereon, wherein the computer program instructions, when executed by a processor, implement an image processing method, the method comprising:
 performing a feature equalization processing on a sample image by an equalization subnetwork of a detection network to obtain an equalized feature image of the sample image, the detection network including the equalization subnetwork and a detection subnetwork;   performing a target detection processing on the equalized feature image by the detection subnetwork to obtain a plurality of predicted regions of a target object in the equalized feature image;   determining an intersection-over-union of each of the plurality of predicted regions respectively, wherein the intersection-over-union is an area ratio of an overlapping region to a merged region of a predicted region of the target object and a corresponding labeled region in the sample image;   sampling the plurality of predicted regions according to the intersection-over-union of each of the predicted regions to obtain a target region; and   training the detection network according to the target region and the labeled region.